A supervised learning method for tempo estimation of musical audio

Automatic tempo estimation for musical audio with low pulse clarity presents challenges. In order to increase the pulse clarity of the input audio signals, the proposed method applies source filtering, especially low pass filtering, to the raw audio, so there are multiple audio clips for the process...

Full description

Saved in:
Bibliographic Details
Main Authors: Wu, Fu-Hai Frank, Jang, Jyh-Shing Roger
Format: Conference Proceeding
Language:English
Subjects:
Accuracy
Estimation
Feature extraction
Filtering
Indexes
Long-Term Periodicity (LTP)
Mathematical model
Pulse Clarity
Tempo Estimation
Tempo-Pair Model
Tempogram
Training
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 604
container_issue
container_start_page 599
container_title
container_volume
creator Wu, Fu-Hai Frank
Jang, Jyh-Shing Roger
description Automatic tempo estimation for musical audio with low pulse clarity presents challenges. In order to increase the pulse clarity of the input audio signals, the proposed method applies source filtering, especially low pass filtering, to the raw audio, so there are multiple audio clips for the processes. These processes are based on tempogram derived from onset detection function to obtain the tempo pair, which is the output of tempo-pair estimator, and their relative strength by the long-term periodicity (LTP) function. Finally, a classifier-based selector chooses the best estimated results from the different paths of audio. The performance of 1 st place in at-least-one-tempo-correct index and 2 nd place in P-score index in the evaluation MIREX 2013 audio tempo estimation demonstrate the effectiveness of the proposed method to audio tempo estimation.
doi_str_mv 10.1109/MED.2014.6961438
format conference_proceeding
fullrecord <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_6961438</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6961438</ieee_id><sourcerecordid>6961438</sourcerecordid><originalsourceid>FETCH-LOGICAL-i175t-e7c48ea98300424b832505f05e78d888e307031d09925aa7c4308584ac2b23cb3</originalsourceid><addsrcrecordid>eNpVj01LxDAURSMiKGP3gpv8gdaXr-ZlOY7jKIy40fWQtq8aaZvStIL_3gFn4-py4XA5l7EbAYUQ4O5etg-FBKGL0pVCKzxjmbMotHXOOBDq_F-H8pJlKX0BgHAlGiev2P2ap2Wk6TskanhHfhrC8MF7mj9jw9s48Zn6MXJKc-j9HOLAY8v7JYXad9wvTYjX7KL1XaLslCv2_rh92zzl-9fd82a9z4OwZs7J1hrJO1QAWuoKlTRgWjBksUFEUmBBiQack8b7I60ADWpfy0qqulIrdvu3G4joME5Hn-nncHqufgG8OUqk</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>A supervised learning method for tempo estimation of musical audio</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Wu, Fu-Hai Frank ; Jang, Jyh-Shing Roger</creator><creatorcontrib>Wu, Fu-Hai Frank ; Jang, Jyh-Shing Roger</creatorcontrib><description>Automatic tempo estimation for musical audio with low pulse clarity presents challenges. In order to increase the pulse clarity of the input audio signals, the proposed method applies source filtering, especially low pass filtering, to the raw audio, so there are multiple audio clips for the processes. These processes are based on tempogram derived from onset detection function to obtain the tempo pair, which is the output of tempo-pair estimator, and their relative strength by the long-term periodicity (LTP) function. Finally, a classifier-based selector chooses the best estimated results from the different paths of audio. The performance of 1 st place in at-least-one-tempo-correct index and 2 nd place in P-score index in the evaluation MIREX 2013 audio tempo estimation demonstrate the effectiveness of the proposed method to audio tempo estimation.</description><identifier>ISBN: 9781479959006</identifier><identifier>ISBN: 1479959006</identifier><identifier>EISBN: 9781479959013</identifier><identifier>EISBN: 1479959014</identifier><identifier>DOI: 10.1109/MED.2014.6961438</identifier><language>eng</language><publisher>IEEE</publisher><subject>Accuracy ; Estimation ; Feature extraction ; Filtering ; Indexes ; Long-Term Periodicity (LTP) ; Mathematical model ; Pulse Clarity ; Tempo Estimation ; Tempo-Pair Model ; Tempogram ; Training</subject><ispartof>22nd Mediterranean Conference on Control and Automation, 2014, p.599-604</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/6961438$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,776,780,785,786,2052,27902,54895</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6961438$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Wu, Fu-Hai Frank</creatorcontrib><creatorcontrib>Jang, Jyh-Shing Roger</creatorcontrib><title>A supervised learning method for tempo estimation of musical audio</title><title>22nd Mediterranean Conference on Control and Automation</title><addtitle>MED</addtitle><description>Automatic tempo estimation for musical audio with low pulse clarity presents challenges. In order to increase the pulse clarity of the input audio signals, the proposed method applies source filtering, especially low pass filtering, to the raw audio, so there are multiple audio clips for the processes. These processes are based on tempogram derived from onset detection function to obtain the tempo pair, which is the output of tempo-pair estimator, and their relative strength by the long-term periodicity (LTP) function. Finally, a classifier-based selector chooses the best estimated results from the different paths of audio. The performance of 1 st place in at-least-one-tempo-correct index and 2 nd place in P-score index in the evaluation MIREX 2013 audio tempo estimation demonstrate the effectiveness of the proposed method to audio tempo estimation.</description><subject>Accuracy</subject><subject>Estimation</subject><subject>Feature extraction</subject><subject>Filtering</subject><subject>Indexes</subject><subject>Long-Term Periodicity (LTP)</subject><subject>Mathematical model</subject><subject>Pulse Clarity</subject><subject>Tempo Estimation</subject><subject>Tempo-Pair Model</subject><subject>Tempogram</subject><subject>Training</subject><isbn>9781479959006</isbn><isbn>1479959006</isbn><isbn>9781479959013</isbn><isbn>1479959014</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2014</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNpVj01LxDAURSMiKGP3gpv8gdaXr-ZlOY7jKIy40fWQtq8aaZvStIL_3gFn4-py4XA5l7EbAYUQ4O5etg-FBKGL0pVCKzxjmbMotHXOOBDq_F-H8pJlKX0BgHAlGiev2P2ap2Wk6TskanhHfhrC8MF7mj9jw9s48Zn6MXJKc-j9HOLAY8v7JYXad9wvTYjX7KL1XaLslCv2_rh92zzl-9fd82a9z4OwZs7J1hrJO1QAWuoKlTRgWjBksUFEUmBBiQack8b7I60ADWpfy0qqulIrdvu3G4joME5Hn-nncHqufgG8OUqk</recordid><startdate>201406</startdate><enddate>201406</enddate><creator>Wu, Fu-Hai Frank</creator><creator>Jang, Jyh-Shing Roger</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>201406</creationdate><title>A supervised learning method for tempo estimation of musical audio</title><author>Wu, Fu-Hai Frank ; Jang, Jyh-Shing Roger</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i175t-e7c48ea98300424b832505f05e78d888e307031d09925aa7c4308584ac2b23cb3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2014</creationdate><topic>Accuracy</topic><topic>Estimation</topic><topic>Feature extraction</topic><topic>Filtering</topic><topic>Indexes</topic><topic>Long-Term Periodicity (LTP)</topic><topic>Mathematical model</topic><topic>Pulse Clarity</topic><topic>Tempo Estimation</topic><topic>Tempo-Pair Model</topic><topic>Tempogram</topic><topic>Training</topic><toplevel>online_resources</toplevel><creatorcontrib>Wu, Fu-Hai Frank</creatorcontrib><creatorcontrib>Jang, Jyh-Shing Roger</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEL</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Wu, Fu-Hai Frank</au><au>Jang, Jyh-Shing Roger</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>A supervised learning method for tempo estimation of musical audio</atitle><btitle>22nd Mediterranean Conference on Control and Automation</btitle><stitle>MED</stitle><date>2014-06</date><risdate>2014</risdate><spage>599</spage><epage>604</epage><pages>599-604</pages><isbn>9781479959006</isbn><isbn>1479959006</isbn><eisbn>9781479959013</eisbn><eisbn>1479959014</eisbn><abstract>Automatic tempo estimation for musical audio with low pulse clarity presents challenges. In order to increase the pulse clarity of the input audio signals, the proposed method applies source filtering, especially low pass filtering, to the raw audio, so there are multiple audio clips for the processes. These processes are based on tempogram derived from onset detection function to obtain the tempo pair, which is the output of tempo-pair estimator, and their relative strength by the long-term periodicity (LTP) function. Finally, a classifier-based selector chooses the best estimated results from the different paths of audio. The performance of 1 st place in at-least-one-tempo-correct index and 2 nd place in P-score index in the evaluation MIREX 2013 audio tempo estimation demonstrate the effectiveness of the proposed method to audio tempo estimation.</abstract><pub>IEEE</pub><doi>10.1109/MED.2014.6961438</doi><tpages>6</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier ISBN: 9781479959006
ispartof 22nd Mediterranean Conference on Control and Automation, 2014, p.599-604
issn
language eng
recordid cdi_ieee_primary_6961438
source IEEE Electronic Library (IEL) Conference Proceedings
subjects Accuracy
Estimation
Feature extraction
Filtering
Indexes
Long-Term Periodicity (LTP)
Mathematical model
Pulse Clarity
Tempo Estimation
Tempo-Pair Model
Tempogram
Training
title A supervised learning method for tempo estimation of musical audio
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-04T14%3A35%3A10IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=A%20supervised%20learning%20method%20for%20tempo%20estimation%20of%20musical%20audio&rft.btitle=22nd%20Mediterranean%20Conference%20on%20Control%20and%20Automation&rft.au=Wu,%20Fu-Hai%20Frank&rft.date=2014-06&rft.spage=599&rft.epage=604&rft.pages=599-604&rft.isbn=9781479959006&rft.isbn_list=1479959006&rft_id=info:doi/10.1109/MED.2014.6961438&rft.eisbn=9781479959013&rft.eisbn_list=1479959014&rft_dat=%3Cieee_6IE%3E6961438%3C/ieee_6IE%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i175t-e7c48ea98300424b832505f05e78d888e307031d09925aa7c4308584ac2b23cb3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=6961438&rfr_iscdi=true